Detection of incidental pulmonary nodules (IPNs), besides lung cancer screening (LCS) programs, is key in early lung cancer detection and reducing lung cancer mortality. Computer-aided IPN detection was boosted by artificial intelligence (AI), promising important technical support for the radiological workup. In this study, we retrospectively studied the precision of two AI-based, computer-aided IPN detection systems on routine computed tomography (CT) scans at three German radiological centers. Within the 1552 CT datasets included in this study, the two AI-based detection systems detected IPN of any size in ca. 70% of the cases with an average of 2 IPN per CT. IPN of relevant size categories ≥5 mm and ≥8 mm was detected in approximately 60% and 35% of the patients, respectively. Manual IPN review by experienced radiologists revealed a low precision of the detection results of only 20 to 70%, with a good comparability between both systems and high variability between the centers. Besides inter-reader variability and site-specific differences in defining IPNs, homogeneity of the mostly LCS-based AI training datasets, together with the high rate of contrast agent usage and comorbidities under real-world conditions, appear as likely causes. Since detection systems are tuned for high sensitivity, our study supports the general usability of such systems in clinical routines. However, the results emphasize the importance to incorporate more diverse real-world data into AI training datasets to further reduce false positive rates and the inherent danger of unnecessary follow-up interventions.
References
[1]
Krebs in Deutschland für 2019/2020 (2023) Robert Koch Institut, Zentrum für Krebsregisterdaten. https://www.krebsdaten.de/Krebs/DE/Content/Publikationen/Krebs_in_Deutschland/krebs_in_deutschland_2023.pdf?__blob=publicationFile
[2]
de Koning, H.J., van der Aalst, C.M., de Jong, P.A., Scholten, E.T., Nackaerts, K., Heuvelmans, M.A., et al. (2020) Reduced Lung-Cancer Mortality with Volume CT Screening in a Randomized Trial. The New England Journal of Medicine, 382, 503-513. https://doi.org/10.1056/NEJMoa1911793
[3]
Field, J.K., Vulkan, D., Davies, M.P.A., Baldwin, D.R., Brain, K.E., Devaraj, A., et al. (2021) Lung Cancer Mortality Reduction by LDCT Screening: UKLS Randomised Trial Results and International Meta-Analysis. The Lancet Regional Health—Europe, 10, Article ID: 100179. https://doi.org/10.1016/j.lanepe.2021.100179
[4]
Bonney, A., Malouf, R., Marchal, C., Manners, D., Fong, K.M., Marshall, H.M., et al. (2022) Impact of Low-Dose Computed Tomography (LDCT) Screening on Lung Cancer-Related Mortality. About the Cochrane Database of Systematic Reviews, 8, CD013829. https://doi.org/10.1002/14651858.CD013829.pub2
[5]
Vogel-Claussen, J., Lasch, F., Bollmann, B.A., May, K., Kuhlmann, A., Schmid-Bindert, G., et al. (2022) Design and Rationale of the HANSE Study: A Holistic German Lung Cancer Screening Trial Using Low-Dose Computed Tomography. RöFo-Fortschritte auf dem Gebiet der R, 194, 1333-1345. https://doi.org/10.1055/a-1853-8291
[6]
Tammemägi, M.C., Katki, H.A., Hocking, W.G., Church, T.R., Caporaso, N., Kvale, P.A., et al. (2013) Selection Criteria for Lung-Cancer Screening. The New England Journal of Medicine, 368, 728-736. https://doi.org/10.1056/NEJMoa1211776
[7]
Hüsing, A. and Kaaks, R. (2020) Risk Prediction Models versus Simplified Selection Criteria to Determine Eligibility for Lung Cancer Screening: An Analysis of German Federal-Wide Survey and Incidence Data. European Journal of Epidemiology, 35, 899-912. https://doi.org/10.1007/s10654-020-00657-w
[8]
Horeweg, N., Scholten, E.T., de Jong, P.A., van der Aalst, C.M., Weenink, C., Lammers, J.W.J., et al. (2014) Detection of Lung Cancer through Low-Dose CT Screening (NELSON): A Prespecified Analysis of Screening Test Performance and Interval Cancers. The Lancet Oncology, 15, 1342-1350. https://doi.org/10.1016/S1470-2045(14)70387-0
[9]
Bundesministerium für Umwelt, Naturschutz, Nukleare Sicherheit und Verbraucherschutz (2024) Bundesumweltministerium lässt künftig Lungenkrebsfrüherkennung mittels Niedrigdosis-Computertomographie zu. https://www.bmuv.de/PM11003
[10]
Bundesministerium für Umwelt, Naturschutz, Nukleare Sicherheit und Verbraucherschutz (2024) Verordnung über die Zulässigkeit der Anwendung der Niedrigdosis-Computertomographie zur Früherkennung von Lungenkrebs bei rauchenden Personen (Lungenkrebs-Früherkennungs-Verordnung—LuKrFrühErkV). https://www.recht.bund.de/bgbl/1/2024/162/VO.html
[11]
Shiraishi, J., Li, Q., Appelbaum, D. and Doi, K. (2011) Computer-Aided Diagnosis and Artificial Intelligence in Clinical Imaging. Seminars in Nuclear Medicine, 41, 449-462. https://doi.org/10.1053/j.semnuclmed.2011.06.004
[12]
Gu, Y., Chi, J., Liu, J., Yang, L., Zhang, B., Yu, D., et al. (2021) A Survey of Computer-aided Diagnosis of Lung Nodules from CT Scans Using Deep Learning. Computers in Biology and Medicine, 137, Article ID: 104806. https://doi.org/10.1016/j.compbiomed.2021.104806
[13]
Goo, J.M. (2011) A Computer-Aided Diagnosis for Evaluating Lung Nodules on Chest CT: The Current Status and Perspective. Korean Journal of Radiology, 12, 145-155. https://doi.org/10.3348/kjr.2011.12.2.145
[14]
Shaukat, F., Raja, G. and Frangi, A.F. (2019) Computer-Aided Detection of Lung Nodules: A Review. Journal of Medical Imaging, 6, Article ID: 020901. https://doi.org/10.1117/1.JMI.6.2.020901
[15]
Fraioli, F., Serra, G. and Passariello, R. (2010) CAD (Computed-Aided Detection) and CADx (Computer Aided Diagnosis) Systems in Identifying and Characterising Lung Nodules on Chest CT: Overview of Research, Developments and New Prospects. La Radiologia Medica, 115, 385-402. https://doi.org/10.1007/s11547-010-0507-2
[16]
de Margerie-Mellon, C. and Chassagnon, G. (2023) Artificial Intelligence: A Critical Review of Applications for Lung Nodule and Lung Cancer. Diagnostic and Interventional Imaging, 104, 11-17. https://doi.org/10.1016/j.diii.2022.11.007
[17]
Cellina, M., Cacioppa, L.M., Cè, M., Chiarpenello, V., Costa, M., Vincenzo, Z., et al. (2023) Artificial Intelligence in Lung Cancer Screening: The Future Is Now. Cancers (Basel), 15, Article 4344. https://doi.org/10.3390/cancers15174344
[18]
Akila Agnes, S., Anitha, J. and Arun Solomon, A. (2022) Two-Stage Lung Nodule Detection Framework Using Enhanced UNet and Convolutional LSTM Networks in CT Images. Computers in Biology and Medicine, 149, Article ID: 106059. https://doi.org/10.1016/j.compbiomed.2022.106059
[19]
Nam, J.G., Hwang, E.J., Kim, J., Park, N., Lee, E.H., Kim, H.J., et al. (2023) AI Improves Nodule Detection on Chest Radiographs in a Health Screening Population: A Randomized Controlled Trial. Radiology, 307, e221894. https://doi.org/10.1148/radiol.221894
[20]
Chamberlin, J., Kocher, M.R., Waltz, J., Snoddy, M., Stringer, N.F.C., Stephenson, J., et al. (2021) Automated Detection of Lung Nodules and Coronary Artery Calcium Using Artificial Intelligence on Low-Dose CT Scans for Lung Cancer Screening: Accuracy and Prognostic Value. BMC Medicine, 19, Article No. 55. https://doi.org/10.1186/s12916-021-01928-3
[21]
Fischer, A.M., Yacoub, B., Savage, R.H., Martinez, J.D., Wichmann, J.L., Sahbaee, P., et al. (2020) Machine Learning/Deep Neuronal Network: Routine Application in Chest Computed Tomography and Workflow Considerations. Journal of Thoracic Imaging, 35, S21-S27. https://doi.org/10.1097/RTI.0000000000000498
[22]
Ciompi, F., Chung, K., van Riel, S.J., Setio, A.A.A., Gerke, P.K., Jacobs, C., et al. (2017) Towards Automatic Pulmonary Nodule Management in Lung Cancer Screening with Deep Learning. Scientific Reports, 7, Article No. 46479. https://doi.org/10.1038/srep46479
[23]
Ardila, D., Kiraly, A.P., Bharadwaj, S., Choi, B., Reicher, J.J., Peng, L., et al. (2019) End-to-End Lung Cancer Screening with Three-Dimensional Deep Learning on Low-dose Chest Computed Tomography. Nature Medicine, 25, 954-961. https://doi.org/10.1038/s41591-019-0447-x
[24]
van Leeuwen, K.G., Schalekamp, S., Rutten, M.J.C.M., van Ginneken, B. and de Rooij, M. (2021) Artificial Intelligence in Radiology: 100 Commercially Available Products and Their Scientific Evidence. European Radiology, 31, 3797-3804. https://doi.org/10.1007/s00330-021-07892-z
[25]
Koçak, B., Ponsiglione, A., Stanzione, A., Bluethgen, C., Santinha, J., Ugga, L., et al. (2024) Bias in Artificial Intelligence for Medical Imaging: Fundamentals, Detection, Avoidance, Mitigation, Challenges, Ethics, and Prospects. Diagnostic and Interventional Radiology, 31, 75-88. https://doi.org/10.4274/dir.2024.242854
[26]
Schreuder, A., Scholten, E.T., van Ginneken, B. and Jacobs, C. (2021) Artificial Intelligence for Detection and Characterization of Pulmonary Nodules in Lung Cancer CT Screening: Ready for Practice? Translational Lung Cancer Research, 10, 2378-2388. https://doi.org/10.21037/tlcr-2020-lcs-06
[27]
Sun, S., Schiller, J.H. and Gazdar, A.F. (2007) Lung Cancer in Never Smokers—A Different Disease. Nature Reviews Cancer, 7, 778-790. https://doi.org/10.1038/nrc2190
[28]
Corrales, L., Rosell, R., Cardona, A.F., Martín, C., Zatarain-Barrón, Z.L. and Arrieta, O. (2020) Lung Cancer in Never Smokers: The Role of Different Risk Factors Other than Tobacco Smoking. Critical Reviews in Oncology/Hematology, 148, Article ID: 102895. https://doi.org/10.1016/j.critrevonc.2020.102895
[29]
Schmid-Bindert, G., Vogel-Claussen, J., Gütz, S., Fink, J., Hoffmann, H., Eichhorn, M.E., et al. (2022) Incidental Pulmonary Nodules—What Do We Know in 2022. Respiration, 101, 1024-1034. https://doi.org/10.1159/000526818
[30]
Arbeitsgemeinschaft der Wissenschaftlichen Medizinischen Fachgesellschaften e. V. (AWMF), Deutschen Krebsgesellschaft e. V. (DKG) und der Stiftung Deutsche Krebshilfe (DKH) (2024) S3-Leitlinie Prävention, Diagnostik, Therapie und Nachsorge des Lungenkarzinoms. https://www.leitlinienprogramm-onkologie.de/fileadmin/user_upload/Downloads/Leitlinien/Lungenkarzinom/Version_3/LL_Lungenkarzinom_Langversion_3.0.pdf
[31]
Mazzone, P.J. and Lam, L. (2022) Evaluating the Patient with a Pulmonary Nodule: A Review. JAMA, 327, 264-273. https://doi.org/10.1001/jama.2021.24287
[32]
MacMahon, H., Naidich, D.P., Goo, J.M., Lee, K.S., Leung, A.N.C., Mayo, J.R., et al. (2017) Guidelines for Management of Incidental Pulmonary Nodules Detected on CT Images: From the Fleischner Society 2017. Radiology, 284, 228-243. https://doi.org/10.1148/radiol.2017161659
[33]
Hendrix, W., Rutten, M., Hendrix, N., van Ginneken, B., Schaefer-Prokop, C., Scholten, E.T., et al. (2023) Trends in the Incidence of Pulmonary Nodules in Chest Computed Tomography: 10-Year Results from Two Dutch Hospitals. European Radiology, 33, 8279-8288. https://doi.org/10.1007/s00330-023-09826-3
[34]
Gould, M.K., Tang, T., Liu, I.L.A., Lee, J., Zheng, C., Danforth, K.N., et al. (2015) Recent Trends in the Identification of Incidental Pulmonary Nodules. American Journal of Respiratory and Critical Care Medicine, 192, 1208-1214. https://doi.org/10.1164/rccm.201505-0990OC
[35]
Marrer, É., Jolly, D., Arveux, P., Lejeune, C., Woronoff-Lemsi, M.C., Jégu, J., et al. (2017) Incidence of Solitary Pulmonary Nodules in Northeastern France: A Population-Based Study in Five Regions. BMC Cancer, 17, Article No. 47. https://doi.org/10.1186/s12885-016-3029-z
[36]
Glandorf, J. and Vogel-Claussen, J. (2024) Incidental Pulmonary Nodules—Current Guidelines and Management. Fortschr Röntgenstr, 196, 582-590. https://doi.org/10.1055/a-2185-8714
[37]
Geppert, J., Asgharzadeh, A., Brown, A., Stinton, C., Helm, E.J., Jayakody, S., et al. (2024) Software Using Artificial Intelligence for Nodule and Cancer Detection in CT Lung Cancer Screening: Systematic Review of Test Accuracy Studies. Thorax, 79, 1040-1049. https://doi.org/10.1136/thorax-2024-221662
